A practical generative adversarial network architecture for restoring damaged character photographs

Hufei Yu,Yifeng Liu,Shiwen He,Pei Jiang,Jiang Xin,Jingxi Wen

Neurocomputing（2021）

引用 2|浏览36

暂无评分

摘要

•We collect real world DCPs, unpaired CCPs, and dirty masks and proposed a residual U-Net GAN.•We put forward a residual U-Net conditional GAN to restore real DCPs.•We adopt a weighted multi-features loss to improve the quality of generated photographs.

查看译文

关键词

Damaged photographs restoration,Deep learning,GAN

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要